{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CVBEYW2U4TKXTAL3BRMQGMS3PA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"acdbad1d86bb04f93f9fcd982ea457c19ae46efb28a61fbed4969d085e1dd223","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-09T17:20:54Z","title_canon_sha256":"e9f379c740165d34707b996c94f28a4202933f5fc09182244e3ba2c209328a61"},"schema_version":"1.0","source":{"id":"2508.07048","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07048","created_at":"2026-06-10T01:09:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07048v2","created_at":"2026-06-10T01:09:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07048","created_at":"2026-06-10T01:09:20Z"},{"alias_kind":"pith_short_12","alias_value":"CVBEYW2U4TKX","created_at":"2026-06-10T01:09:20Z"},{"alias_kind":"pith_short_16","alias_value":"CVBEYW2U4TKXTAL3","created_at":"2026-06-10T01:09:20Z"},{"alias_kind":"pith_short_8","alias_value":"CVBEYW2U","created_at":"2026-06-10T01:09:20Z"}],"graph_snapshots":[{"event_id":"sha256:c53de8bbd2b29140631583b8fb95dede987fc3fb2292f430e04cf80c811b59c9","target":"graph","created_at":"2026-06-10T01:09:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.07048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length. A natural alternative, CTC-style non-autoregressive (NAR) systems avoid this bottleneck but their conditional independence assumption sacrifices transcript-level generative modeling. Masked diffusion language models (e.g., LLaDA, MDLM) offer a competitive NAR text-generation approach. We ask whether such models can bring NAR ASR into the accuracy regime of strong AR ASR systems while removing the left-to-right bottleneck. We pr","authors_text":"Heeju Jwa, Hyuk-jae Lee, Hyungon Ryu, Jongchan Kim, Junhyuk Ahn, Nam-Joon Kim, Siwon Park, Taegeun Yun, Taeyoun Kwon, Yoonchae Choi","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-09T17:20:54Z","title":"Whisfusion: Parallel ASR Decoding with Masked Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07048","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11ef591a37a3ed998f5ec99d9b7452cf9ae9678ec3efaeda12217270b0e67e6f","target":"record","created_at":"2026-06-10T01:09:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"acdbad1d86bb04f93f9fcd982ea457c19ae46efb28a61fbed4969d085e1dd223","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-09T17:20:54Z","title_canon_sha256":"e9f379c740165d34707b996c94f28a4202933f5fc09182244e3ba2c209328a61"},"schema_version":"1.0","source":{"id":"2508.07048","kind":"arxiv","version":2}},"canonical_sha256":"15424c5b54e4d579817b0c5903325b7812382bd1117903c45aafb9e536057aa7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15424c5b54e4d579817b0c5903325b7812382bd1117903c45aafb9e536057aa7","first_computed_at":"2026-06-10T01:09:20.851606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:20.851606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3vTKt+L1GB03YaGl5nHG0ne7u23Yqvwo3ix+pmtgMmLpiaVG4Jw1ZjQiZaclIlW4yGpvCLWelrxIgIZE73KbCg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:20.852713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07048","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ef591a37a3ed998f5ec99d9b7452cf9ae9678ec3efaeda12217270b0e67e6f","sha256:c53de8bbd2b29140631583b8fb95dede987fc3fb2292f430e04cf80c811b59c9"],"state_sha256":"56f1dd67eb4cfdd281de64dd005ab29afacdcf0687a81e27da01bd21afa54ef8"}